© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 6053
    Prev
    Next
    INDEX
    Explanations

    environments and settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    estr
    -0.09
    ervals
    -0.09
     SHIFT
    -0.09
     Pou
    -0.08
     goodies
    -0.08
     trophies
    -0.08
    SHIFT
    -0.08
     SI
    -0.08
     accord
    -0.08
     Lightweight
    -0.08
    POSITIVE LOGITS
     environments
    0.44
     environment
    0.44
     setting
    0.42
     settings
    0.42
     situations
    0.35
     contexts
    0.35
     situation
    0.35
     context
    0.34
     envi
    0.33
     Settings
    0.31
    Activations Density 0.511%

    No Known Activations